COMP-4640 Intelligent & Interactive Systems Lecture 1

1. COMP-4640 Intelligent & Interactive Systems Lecture 1 Cheryl Seals, Ph.D. Computer Science & Software Engineering Auburn University

2. Artificial Intelligence What is Artificial Intelligence? • “Artificial Intelligence is the area of computer science concerned with intelligent behavior in artifacts and involves perception, reasoning, learning, communicating, and acting in complex environments” (Nilsson 1998). • “Artificial Intelligence is the study of ways in which computers can be made to perform cognitive tasks, at which, at present, people are better” (Elaine Rich, Encyclopedia of AI) • 4 categories of AI based on whether an agent thinks/acts humanly/rationally. Goals of AI • Develop machines that can do things just as good if not better than humans • The understanding of intelligent systems.

3. Artificial Intelligence: Chapter1 One question we must ask ourselves is: “Can machines think?” • Are humans machines? • Are other animals, insects, viruses, bacteria, machines? • Can thinking only occur in special types (protein-based) machines (John Searle)? • Physical Symbol System Hypothesis (Newell & Simon), “A physical symbol system has the necessary and sufficient means for intelligent action. What types of machines are needed to facilitate “Intelligence”? • Parallel machines rather than single processor systems? • Fuzzy Logic rather than Boolean Logic? • Artificial neurons rather than switches?

4. Artificial Intelligence: Chapter1 What does it mean to think? (Rather than answering this question directly Alan Turing developed a Test) • The Turing Test takes place between (1) a machine, (2) a human, and (3) an interrogator. • The interrogator can communicate with the machine and the human via a teletype. • The objective of the interrogator is to ask a series of questions and then determine which is the human and which is the machine. • The objective of the machine is to make the interrogator make the wrong identification. • The objective of the human is to help the interrogator make the correct decision. • Often however this test has been simplified to one where the computer tries to convince a human interrogator. • Eliza (Weizenbaum, 1965), • PARRY (Colby, 1971)

5. Artificial Intelligence: Chapter1 If a machine could pass the Turing Test, what type of capabilities would it need to possess? • Search for Solutions (depth-first, A*, Branch & Bound, Beam, etc.) [Chapters 3, 4 & 5] • Knowledge Representation [Chapters 6 & 7] • Reasoning [Chapters 9 & 10] • Learning (Adaptation) [Genetic Algorithms] • Natural Language Understanding • Computer Vision • Computer Hearing • Robotics • Smell (Electronic Nose) • Consciousness? • Emotions?

6. Approaches to Artificial Intelligence • Symbol-Processing Approach • Based on Newell & Simons Physical Symbol System Hypothesis • Uses logical operations that are applied to declarative knowledge bases (FOPL) • Commonly referred to as “Classical AI” • Represents knowledge about a problem as a set of declarative sentences in FOPL • Then logical reasoning methods are used to deduce consequences • Another name for this type of approach is called “the knowledge-based” approach • In most knowledge-based systems, the analysis and development of programs to achieve a targeted behavior is based on layered implementation: • Knowledge Layer – contains the knowledge needed by the machine or system • Symbol Layer – is where the knowledge is represented in symbolic structures, and where operations on these structures are defined. • Lower Layers – this is where the operations are actually implemented • The Symbol Processing Approach uses “top-down” design of intelligent behavior.

7. Approaches to Artificial Intelligence • Subsymbolic Approach • usually proceeds in “bottom-up” style. • Starting at the lowest layers and working upward. • In the subsymbolic approach signals are generally used rather than symbols • The most popular subsymbolic approach is called the “animat approach” • Proponents of this stress that human intelligence came as a result of billions of years of evolution. • Therefore, the development of machine intelligence must follow many of the same evolutionary steps. • Much work on animat-systems has concentrated on the signal processing abilities of simple animals. The goal of course is to move up the animal (animat) chain. • Subsymbolic approaches rely primarily on interaction between machine and environment. This interaction produces and emergent behavior (evolutionary robotics, Nordin, Lund) • Some other subsymbolic approaches are: Neural Networks and Genetic Algorithms

8. A Brief History of Artificial Intelligence Before It was Called AI (1943-1956) • The first “AI” type work was that of McCulloch & Pitts. They are credited with developing the first neural network application. Also David Hebb (1949) performed some pioneering work on weight reinforcement (Hebbian Learning). • Shannon (1950) and Turing (1953) were developing programs for playing Chess. • Minsky & Edmonds (1951) developed the first neural computer, the SNARC. • Minsky later co-authored a book, Perceptrons (Minsky & Papert 1969). In this book, Minsky & Papert proved that single layer neural networks, which were widely used and researched at the time, were theoretically incapable of solving many simple problems, in the exclusive-or function.

9. A Brief History of Artificial Intelligence • In 1956, John McCarthy & Claude Shannon co-edited a volume entitled “Automata Studies”. However, McCarthy was disappointed that the papers submitted dealt mainly with the theory of automata. • Later in 1956, McCarthy used the phrase “Artificial Intelligence” as the title of a conference at Dartmouth. • Other names that were tried for this new field were: • Complex Information Processing • Machine Intelligence • Heuristic Programming • Cognology

10. A Brief History of Artificial Intelligence Early Successes (1952-1969) • During this period a number of AI pioneers developed a number successful “Intelligent Systems” • Newell & Simon’s General Problem Solver (GPS) successfully imitated the human problem solving process (Thinking Humanly Approach). • Nathaniel Rochester developed numerous AI programs at IBM. • Gelernter (1959) developed the Geometry Theorem Prover (which was similar in spirit to the Logic Theorist). • Samuel (1952) developed a Checkers program that eventually learned to play tournament level Checkers. This was the first AI system that could outperform its creator.

11. A Brief History of Artificial Intelligence Early Successes (1952-1969) cont. • McCarthy left Dartmouth for MIT and in 1958 • Developed LISP (1958) • Invented Time Sharing (1958) (Some of his student went on to develop a company called Digital Equipment Corporation). • Developed Advice Taker (1958) one of the first systems that embodied knowledge representation & reason. • Cordell Green – Green’s Theorem (Clause) Question answering planning systems (1969)

12. A Brief History of Artificial Intelligence A Dose of Reality (1966-1974) • Due to the early success of many pioneering researchers, a number of overly optimistic claims were made about the future of AI. • When the AI community failed to deliver on their claims many funding agencies lost interest. • Basically, three kinds of difficulties arose that set the stage for this 1st setback • Programs were not knowledge-based systems; many programs like Eliza and PARRY used a number of “tricks” and used little of the existing AI-techniques. • Many of the successful AI applications during this period solve toy problems which were smaller instances of NP-Complete problems. • Minsky’s Perceptons book!

13. A Brief History of Artificial Intelligence The Rise of Expert Systems (1969-1979) • Developers of expert systems used expert knowledge represented as a knowledge base of rules to find solutions for a very specific areas of expertise. • Some successful expert systems during this period were: • Dendral (Feigenbaum, Buchanan, Lederberg) – was able to determine structure of organic molecules based on their chemical formulas and mass spectrographic information about chemical bonds within them. • MYCIN (Feigenbaum, Buchanan, Shortliffe) – was used to diagnose blood infections. • Prospector (Duda) – was used for determining the probable location of ore deposits based on the geological information of a site.

14. A Brief History of Artificial Intelligence AI Becomes an Industry (1980-1989) • A number of factors contributed to the development of the AI during this period. • The success of expert systems like R1 (XCON) by McDermott and Prospector • An ambitious “Fifth Generation Project” proposed by Japan. • A number of companies began to market expert system technology and LISP machines. Return of Neural Networks (1986-Present) • Despite Minsky & Papert’s book, many researchers continued their work in neural networks. • When the back-propagation algorithm was rediscovered for training multi-layer feed-forward neural nets, interest in neural nets began to grow once more.

15. Areas of AI Research (to name just a few) • Game Playing • Automated Reasoning • Expert Systems • Natural Language Processing • Human Performance Modeling • Planning • Robotics • Human-Computer Interaction/Intelligence • Natural Language Processing • Speech Processing • Pattern Recognition (Gestures, eye movements, etc.) • “Intelligent” User Interfaces & Computer-Aided Instruction. • Machine Learning • Neural Computing • Fuzzy Computing • Evolutionary Computing